|
- C:\Users\Mark\anaconda3\envs\detr\python.exe C:\01Code\DINO-ms\test\compare_torch.py
- platform is Windows
- neck.convs.0.conv.weight (256, 512, 1, 1)
- neck.convs.0.conv.bias (256,)
- neck.convs.0.norm.weight (256,)
- neck.convs.0.norm.bias (256,)
- neck.convs.1.conv.weight (256, 1024, 1, 1)
- neck.convs.1.conv.bias (256,)
- neck.convs.1.norm.weight (256,)
- neck.convs.1.norm.bias (256,)
- neck.convs.2.conv.weight (256, 2048, 1, 1)
- neck.convs.2.conv.bias (256,)
- neck.convs.2.norm.weight (256,)
- neck.convs.2.norm.bias (256,)
- neck.extra_convs.0.conv.weight (256, 2048, 3, 3)
- neck.extra_convs.0.conv.bias (256,)
- neck.extra_convs.0.norm.weight (256,)
- neck.extra_convs.0.norm.bias (256,)
- transformer.level_embeds (4, 256)
- transformer.encoder.layers.0.attentions.0.sampling_offsets.weight (256, 256)
- transformer.encoder.layers.0.attentions.0.sampling_offsets.bias (256,)
- transformer.encoder.layers.0.attentions.0.attention_weights.weight (128, 256)
- transformer.encoder.layers.0.attentions.0.attention_weights.bias (128,)
- transformer.encoder.layers.0.attentions.0.value_proj.weight (256, 256)
- transformer.encoder.layers.0.attentions.0.value_proj.bias (256,)
- transformer.encoder.layers.0.attentions.0.output_proj.weight (256, 256)
- transformer.encoder.layers.0.attentions.0.output_proj.bias (256,)
- transformer.encoder.layers.0.ffns.0.layers.0.0.weight (2048, 256)
- transformer.encoder.layers.0.ffns.0.layers.0.0.bias (2048,)
- transformer.encoder.layers.0.ffns.0.layers.1.weight (256, 2048)
- transformer.encoder.layers.0.ffns.0.layers.1.bias (256,)
- transformer.encoder.layers.0.norms.0.weight (256,)
- transformer.encoder.layers.0.norms.0.bias (256,)
- transformer.encoder.layers.0.norms.1.weight (256,)
- transformer.encoder.layers.0.norms.1.bias (256,)
- transformer.encoder.layers.1.attentions.0.sampling_offsets.weight (256, 256)
- transformer.encoder.layers.1.attentions.0.sampling_offsets.bias (256,)
- transformer.encoder.layers.1.attentions.0.attention_weights.weight (128, 256)
- transformer.encoder.layers.1.attentions.0.attention_weights.bias (128,)
- transformer.encoder.layers.1.attentions.0.value_proj.weight (256, 256)
- transformer.encoder.layers.1.attentions.0.value_proj.bias (256,)
- transformer.encoder.layers.1.attentions.0.output_proj.weight (256, 256)
- transformer.encoder.layers.1.attentions.0.output_proj.bias (256,)
- transformer.encoder.layers.1.ffns.0.layers.0.0.weight (2048, 256)
- transformer.encoder.layers.1.ffns.0.layers.0.0.bias (2048,)
- transformer.encoder.layers.1.ffns.0.layers.1.weight (256, 2048)
- transformer.encoder.layers.1.ffns.0.layers.1.bias (256,)
- transformer.encoder.layers.1.norms.0.weight (256,)
- transformer.encoder.layers.1.norms.0.bias (256,)
- transformer.encoder.layers.1.norms.1.weight (256,)
- transformer.encoder.layers.1.norms.1.bias (256,)
- transformer.encoder.layers.2.attentions.0.sampling_offsets.weight (256, 256)
- transformer.encoder.layers.2.attentions.0.sampling_offsets.bias (256,)
- transformer.encoder.layers.2.attentions.0.attention_weights.weight (128, 256)
- transformer.encoder.layers.2.attentions.0.attention_weights.bias (128,)
- transformer.encoder.layers.2.attentions.0.value_proj.weight (256, 256)
- transformer.encoder.layers.2.attentions.0.value_proj.bias (256,)
- transformer.encoder.layers.2.attentions.0.output_proj.weight (256, 256)
- transformer.encoder.layers.2.attentions.0.output_proj.bias (256,)
- transformer.encoder.layers.2.ffns.0.layers.0.0.weight (2048, 256)
- transformer.encoder.layers.2.ffns.0.layers.0.0.bias (2048,)
- transformer.encoder.layers.2.ffns.0.layers.1.weight (256, 2048)
- transformer.encoder.layers.2.ffns.0.layers.1.bias (256,)
- transformer.encoder.layers.2.norms.0.weight (256,)
- transformer.encoder.layers.2.norms.0.bias (256,)
- transformer.encoder.layers.2.norms.1.weight (256,)
- transformer.encoder.layers.2.norms.1.bias (256,)
- transformer.encoder.layers.3.attentions.0.sampling_offsets.weight (256, 256)
- transformer.encoder.layers.3.attentions.0.sampling_offsets.bias (256,)
- transformer.encoder.layers.3.attentions.0.attention_weights.weight (128, 256)
- transformer.encoder.layers.3.attentions.0.attention_weights.bias (128,)
- transformer.encoder.layers.3.attentions.0.value_proj.weight (256, 256)
- transformer.encoder.layers.3.attentions.0.value_proj.bias (256,)
- transformer.encoder.layers.3.attentions.0.output_proj.weight (256, 256)
- transformer.encoder.layers.3.attentions.0.output_proj.bias (256,)
- transformer.encoder.layers.3.ffns.0.layers.0.0.weight (2048, 256)
- transformer.encoder.layers.3.ffns.0.layers.0.0.bias (2048,)
- transformer.encoder.layers.3.ffns.0.layers.1.weight (256, 2048)
- transformer.encoder.layers.3.ffns.0.layers.1.bias (256,)
- transformer.encoder.layers.3.norms.0.weight (256,)
- transformer.encoder.layers.3.norms.0.bias (256,)
- transformer.encoder.layers.3.norms.1.weight (256,)
- transformer.encoder.layers.3.norms.1.bias (256,)
- transformer.encoder.layers.4.attentions.0.sampling_offsets.weight (256, 256)
- transformer.encoder.layers.4.attentions.0.sampling_offsets.bias (256,)
- transformer.encoder.layers.4.attentions.0.attention_weights.weight (128, 256)
- transformer.encoder.layers.4.attentions.0.attention_weights.bias (128,)
- transformer.encoder.layers.4.attentions.0.value_proj.weight (256, 256)
- transformer.encoder.layers.4.attentions.0.value_proj.bias (256,)
- transformer.encoder.layers.4.attentions.0.output_proj.weight (256, 256)
- transformer.encoder.layers.4.attentions.0.output_proj.bias (256,)
- transformer.encoder.layers.4.ffns.0.layers.0.0.weight (2048, 256)
- transformer.encoder.layers.4.ffns.0.layers.0.0.bias (2048,)
- transformer.encoder.layers.4.ffns.0.layers.1.weight (256, 2048)
- transformer.encoder.layers.4.ffns.0.layers.1.bias (256,)
- transformer.encoder.layers.4.norms.0.weight (256,)
- transformer.encoder.layers.4.norms.0.bias (256,)
- transformer.encoder.layers.4.norms.1.weight (256,)
- transformer.encoder.layers.4.norms.1.bias (256,)
- transformer.encoder.layers.5.attentions.0.sampling_offsets.weight (256, 256)
- transformer.encoder.layers.5.attentions.0.sampling_offsets.bias (256,)
- transformer.encoder.layers.5.attentions.0.attention_weights.weight (128, 256)
- transformer.encoder.layers.5.attentions.0.attention_weights.bias (128,)
- transformer.encoder.layers.5.attentions.0.value_proj.weight (256, 256)
- transformer.encoder.layers.5.attentions.0.value_proj.bias (256,)
- transformer.encoder.layers.5.attentions.0.output_proj.weight (256, 256)
- transformer.encoder.layers.5.attentions.0.output_proj.bias (256,)
- transformer.encoder.layers.5.ffns.0.layers.0.0.weight (2048, 256)
- transformer.encoder.layers.5.ffns.0.layers.0.0.bias (2048,)
- transformer.encoder.layers.5.ffns.0.layers.1.weight (256, 2048)
- transformer.encoder.layers.5.ffns.0.layers.1.bias (256,)
- transformer.encoder.layers.5.norms.0.weight (256,)
- transformer.encoder.layers.5.norms.0.bias (256,)
- transformer.encoder.layers.5.norms.1.weight (256,)
- transformer.encoder.layers.5.norms.1.bias (256,)
- (768, 256) 0 256
- transformer.decoder.layers.0.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 0 256
- transformer.decoder.layers.0.attentions.0.attn.in_proj_bias (256,)
- (768, 256) 256 512
- transformer.decoder.layers.0.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 256 512
- transformer.decoder.layers.0.attentions.0.attn.in_proj_bias (256,)
- (768, 256) 512 768
- transformer.decoder.layers.0.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 512 768
- transformer.decoder.layers.0.attentions.0.attn.in_proj_bias (256,)
- transformer.decoder.layers.0.attentions.0.attn.out_proj.weight (256, 256)
- transformer.decoder.layers.0.attentions.0.attn.out_proj.bias (256,)
- transformer.decoder.layers.0.attentions.1.sampling_offsets.weight (256, 256)
- transformer.decoder.layers.0.attentions.1.sampling_offsets.bias (256,)
- transformer.decoder.layers.0.attentions.1.attention_weights.weight (128, 256)
- transformer.decoder.layers.0.attentions.1.attention_weights.bias (128,)
- transformer.decoder.layers.0.attentions.1.value_proj.weight (256, 256)
- transformer.decoder.layers.0.attentions.1.value_proj.bias (256,)
- transformer.decoder.layers.0.attentions.1.output_proj.weight (256, 256)
- transformer.decoder.layers.0.attentions.1.output_proj.bias (256,)
- transformer.decoder.layers.0.ffns.0.layers.0.0.weight (2048, 256)
- transformer.decoder.layers.0.ffns.0.layers.0.0.bias (2048,)
- transformer.decoder.layers.0.ffns.0.layers.1.weight (256, 2048)
- transformer.decoder.layers.0.ffns.0.layers.1.bias (256,)
- transformer.decoder.layers.0.norms.0.weight (256,)
- transformer.decoder.layers.0.norms.0.bias (256,)
- transformer.decoder.layers.0.norms.1.weight (256,)
- transformer.decoder.layers.0.norms.1.bias (256,)
- transformer.decoder.layers.0.norms.2.weight (256,)
- transformer.decoder.layers.0.norms.2.bias (256,)
- (768, 256) 0 256
- transformer.decoder.layers.1.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 0 256
- transformer.decoder.layers.1.attentions.0.attn.in_proj_bias (256,)
- (768, 256) 256 512
- transformer.decoder.layers.1.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 256 512
- transformer.decoder.layers.1.attentions.0.attn.in_proj_bias (256,)
- (768, 256) 512 768
- transformer.decoder.layers.1.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 512 768
- transformer.decoder.layers.1.attentions.0.attn.in_proj_bias (256,)
- transformer.decoder.layers.1.attentions.0.attn.out_proj.weight (256, 256)
- transformer.decoder.layers.1.attentions.0.attn.out_proj.bias (256,)
- transformer.decoder.layers.1.attentions.1.sampling_offsets.weight (256, 256)
- transformer.decoder.layers.1.attentions.1.sampling_offsets.bias (256,)
- transformer.decoder.layers.1.attentions.1.attention_weights.weight (128, 256)
- transformer.decoder.layers.1.attentions.1.attention_weights.bias (128,)
- transformer.decoder.layers.1.attentions.1.value_proj.weight (256, 256)
- transformer.decoder.layers.1.attentions.1.value_proj.bias (256,)
- transformer.decoder.layers.1.attentions.1.output_proj.weight (256, 256)
- transformer.decoder.layers.1.attentions.1.output_proj.bias (256,)
- transformer.decoder.layers.1.ffns.0.layers.0.0.weight (2048, 256)
- transformer.decoder.layers.1.ffns.0.layers.0.0.bias (2048,)
- transformer.decoder.layers.1.ffns.0.layers.1.weight (256, 2048)
- transformer.decoder.layers.1.ffns.0.layers.1.bias (256,)
- transformer.decoder.layers.1.norms.0.weight (256,)
- transformer.decoder.layers.1.norms.0.bias (256,)
- transformer.decoder.layers.1.norms.1.weight (256,)
- transformer.decoder.layers.1.norms.1.bias (256,)
- transformer.decoder.layers.1.norms.2.weight (256,)
- transformer.decoder.layers.1.norms.2.bias (256,)
- (768, 256) 0 256
- transformer.decoder.layers.2.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 0 256
- transformer.decoder.layers.2.attentions.0.attn.in_proj_bias (256,)
- (768, 256) 256 512
- transformer.decoder.layers.2.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 256 512
- transformer.decoder.layers.2.attentions.0.attn.in_proj_bias (256,)
- (768, 256) 512 768
- transformer.decoder.layers.2.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 512 768
- transformer.decoder.layers.2.attentions.0.attn.in_proj_bias (256,)
- transformer.decoder.layers.2.attentions.0.attn.out_proj.weight (256, 256)
- transformer.decoder.layers.2.attentions.0.attn.out_proj.bias (256,)
- transformer.decoder.layers.2.attentions.1.sampling_offsets.weight (256, 256)
- transformer.decoder.layers.2.attentions.1.sampling_offsets.bias (256,)
- transformer.decoder.layers.2.attentions.1.attention_weights.weight (128, 256)
- transformer.decoder.layers.2.attentions.1.attention_weights.bias (128,)
- transformer.decoder.layers.2.attentions.1.value_proj.weight (256, 256)
- transformer.decoder.layers.2.attentions.1.value_proj.bias (256,)
- transformer.decoder.layers.2.attentions.1.output_proj.weight (256, 256)
- transformer.decoder.layers.2.attentions.1.output_proj.bias (256,)
- transformer.decoder.layers.2.ffns.0.layers.0.0.weight (2048, 256)
- transformer.decoder.layers.2.ffns.0.layers.0.0.bias (2048,)
- transformer.decoder.layers.2.ffns.0.layers.1.weight (256, 2048)
- transformer.decoder.layers.2.ffns.0.layers.1.bias (256,)
- transformer.decoder.layers.2.norms.0.weight (256,)
- transformer.decoder.layers.2.norms.0.bias (256,)
- transformer.decoder.layers.2.norms.1.weight (256,)
- transformer.decoder.layers.2.norms.1.bias (256,)
- transformer.decoder.layers.2.norms.2.weight (256,)
- transformer.decoder.layers.2.norms.2.bias (256,)
- (768, 256) 0 256
- transformer.decoder.layers.3.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 0 256
- transformer.decoder.layers.3.attentions.0.attn.in_proj_bias (256,)
- (768, 256) 256 512
- transformer.decoder.layers.3.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 256 512
- transformer.decoder.layers.3.attentions.0.attn.in_proj_bias (256,)
- (768, 256) 512 768
- transformer.decoder.layers.3.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 512 768
- transformer.decoder.layers.3.attentions.0.attn.in_proj_bias (256,)
- transformer.decoder.layers.3.attentions.0.attn.out_proj.weight (256, 256)
- transformer.decoder.layers.3.attentions.0.attn.out_proj.bias (256,)
- transformer.decoder.layers.3.attentions.1.sampling_offsets.weight (256, 256)
- transformer.decoder.layers.3.attentions.1.sampling_offsets.bias (256,)
- transformer.decoder.layers.3.attentions.1.attention_weights.weight (128, 256)
- transformer.decoder.layers.3.attentions.1.attention_weights.bias (128,)
- transformer.decoder.layers.3.attentions.1.value_proj.weight (256, 256)
- transformer.decoder.layers.3.attentions.1.value_proj.bias (256,)
- transformer.decoder.layers.3.attentions.1.output_proj.weight (256, 256)
- transformer.decoder.layers.3.attentions.1.output_proj.bias (256,)
- transformer.decoder.layers.3.ffns.0.layers.0.0.weight (2048, 256)
- transformer.decoder.layers.3.ffns.0.layers.0.0.bias (2048,)
- transformer.decoder.layers.3.ffns.0.layers.1.weight (256, 2048)
- transformer.decoder.layers.3.ffns.0.layers.1.bias (256,)
- transformer.decoder.layers.3.norms.0.weight (256,)
- transformer.decoder.layers.3.norms.0.bias (256,)
- transformer.decoder.layers.3.norms.1.weight (256,)
- transformer.decoder.layers.3.norms.1.bias (256,)
- transformer.decoder.layers.3.norms.2.weight (256,)
- transformer.decoder.layers.3.norms.2.bias (256,)
- (768, 256) 0 256
- transformer.decoder.layers.4.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 0 256
- transformer.decoder.layers.4.attentions.0.attn.in_proj_bias (256,)
- (768, 256) 256 512
- transformer.decoder.layers.4.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 256 512
- transformer.decoder.layers.4.attentions.0.attn.in_proj_bias (256,)
- (768, 256) 512 768
- transformer.decoder.layers.4.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 512 768
- transformer.decoder.layers.4.attentions.0.attn.in_proj_bias (256,)
- transformer.decoder.layers.4.attentions.0.attn.out_proj.weight (256, 256)
- transformer.decoder.layers.4.attentions.0.attn.out_proj.bias (256,)
- transformer.decoder.layers.4.attentions.1.sampling_offsets.weight (256, 256)
- transformer.decoder.layers.4.attentions.1.sampling_offsets.bias (256,)
- transformer.decoder.layers.4.attentions.1.attention_weights.weight (128, 256)
- transformer.decoder.layers.4.attentions.1.attention_weights.bias (128,)
- transformer.decoder.layers.4.attentions.1.value_proj.weight (256, 256)
- transformer.decoder.layers.4.attentions.1.value_proj.bias (256,)
- transformer.decoder.layers.4.attentions.1.output_proj.weight (256, 256)
- transformer.decoder.layers.4.attentions.1.output_proj.bias (256,)
- transformer.decoder.layers.4.ffns.0.layers.0.0.weight (2048, 256)
- transformer.decoder.layers.4.ffns.0.layers.0.0.bias (2048,)
- transformer.decoder.layers.4.ffns.0.layers.1.weight (256, 2048)
- transformer.decoder.layers.4.ffns.0.layers.1.bias (256,)
- transformer.decoder.layers.4.norms.0.weight (256,)
- transformer.decoder.layers.4.norms.0.bias (256,)
- transformer.decoder.layers.4.norms.1.weight (256,)
- transformer.decoder.layers.4.norms.1.bias (256,)
- transformer.decoder.layers.4.norms.2.weight (256,)
- transformer.decoder.layers.4.norms.2.bias (256,)
- (768, 256) 0 256
- transformer.decoder.layers.5.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 0 256
- transformer.decoder.layers.5.attentions.0.attn.in_proj_bias (256,)
- (768, 256) 256 512
- transformer.decoder.layers.5.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 256 512
- transformer.decoder.layers.5.attentions.0.attn.in_proj_bias (256,)
- (768, 256) 512 768
- transformer.decoder.layers.5.attentions.0.attn.in_proj_weight (256, 256)
- (768,) 512 768
- transformer.decoder.layers.5.attentions.0.attn.in_proj_bias (256,)
- transformer.decoder.layers.5.attentions.0.attn.out_proj.weight (256, 256)
- transformer.decoder.layers.5.attentions.0.attn.out_proj.bias (256,)
- transformer.decoder.layers.5.attentions.1.sampling_offsets.weight (256, 256)
- transformer.decoder.layers.5.attentions.1.sampling_offsets.bias (256,)
- transformer.decoder.layers.5.attentions.1.attention_weights.weight (128, 256)
- transformer.decoder.layers.5.attentions.1.attention_weights.bias (128,)
- transformer.decoder.layers.5.attentions.1.value_proj.weight (256, 256)
- transformer.decoder.layers.5.attentions.1.value_proj.bias (256,)
- transformer.decoder.layers.5.attentions.1.output_proj.weight (256, 256)
- transformer.decoder.layers.5.attentions.1.output_proj.bias (256,)
- transformer.decoder.layers.5.ffns.0.layers.0.0.weight (2048, 256)
- transformer.decoder.layers.5.ffns.0.layers.0.0.bias (2048,)
- transformer.decoder.layers.5.ffns.0.layers.1.weight (256, 2048)
- transformer.decoder.layers.5.ffns.0.layers.1.bias (256,)
- transformer.decoder.layers.5.norms.0.weight (256,)
- transformer.decoder.layers.5.norms.0.bias (256,)
- transformer.decoder.layers.5.norms.1.weight (256,)
- transformer.decoder.layers.5.norms.1.bias (256,)
- transformer.decoder.layers.5.norms.2.weight (256,)
- transformer.decoder.layers.5.norms.2.bias (256,)
- transformer.decoder.ref_point_head.layers.0.weight (256, 512)
- transformer.decoder.ref_point_head.layers.0.bias (256,)
- transformer.decoder.ref_point_head.layers.1.weight (256, 256)
- transformer.decoder.ref_point_head.layers.1.bias (256,)
- transformer.decoder.norm.weight (256,)
- transformer.decoder.norm.bias (256,)
- class_embed.0.weight (80, 256)
- class_embed.0.bias (80,)
- class_embed.1.weight (80, 256)
- class_embed.1.bias (80,)
- class_embed.2.weight (80, 256)
- class_embed.2.bias (80,)
- class_embed.3.weight (80, 256)
- class_embed.3.bias (80,)
- class_embed.4.weight (80, 256)
- class_embed.4.bias (80,)
- class_embed.5.weight (80, 256)
- class_embed.5.bias (80,)
- class_embed.6.weight (80, 256)
- class_embed.6.bias (80,)
- bbox_embed.0.layers.0.weight (256, 256)
- bbox_embed.0.layers.0.bias (256,)
- bbox_embed.0.layers.1.weight (256, 256)
- bbox_embed.0.layers.1.bias (256,)
- bbox_embed.0.layers.2.weight (4, 256)
- bbox_embed.0.layers.2.bias (4,)
- bbox_embed.1.layers.0.weight (256, 256)
- bbox_embed.1.layers.0.bias (256,)
- bbox_embed.1.layers.1.weight (256, 256)
- bbox_embed.1.layers.1.bias (256,)
- bbox_embed.1.layers.2.weight (4, 256)
- bbox_embed.1.layers.2.bias (4,)
- bbox_embed.2.layers.0.weight (256, 256)
- bbox_embed.2.layers.0.bias (256,)
- bbox_embed.2.layers.1.weight (256, 256)
- bbox_embed.2.layers.1.bias (256,)
- bbox_embed.2.layers.2.weight (4, 256)
- bbox_embed.2.layers.2.bias (4,)
- bbox_embed.3.layers.0.weight (256, 256)
- bbox_embed.3.layers.0.bias (256,)
- bbox_embed.3.layers.1.weight (256, 256)
- bbox_embed.3.layers.1.bias (256,)
- bbox_embed.3.layers.2.weight (4, 256)
- bbox_embed.3.layers.2.bias (4,)
- bbox_embed.4.layers.0.weight (256, 256)
- bbox_embed.4.layers.0.bias (256,)
- bbox_embed.4.layers.1.weight (256, 256)
- bbox_embed.4.layers.1.bias (256,)
- bbox_embed.4.layers.2.weight (4, 256)
- bbox_embed.4.layers.2.bias (4,)
- bbox_embed.5.layers.0.weight (256, 256)
- bbox_embed.5.layers.0.bias (256,)
- bbox_embed.5.layers.1.weight (256, 256)
- bbox_embed.5.layers.1.bias (256,)
- bbox_embed.5.layers.2.weight (4, 256)
- bbox_embed.5.layers.2.bias (4,)
- bbox_embed.6.layers.0.weight (256, 256)
- bbox_embed.6.layers.0.bias (256,)
- bbox_embed.6.layers.1.weight (256, 256)
- bbox_embed.6.layers.1.bias (256,)
- bbox_embed.6.layers.2.weight (4, 256)
- bbox_embed.6.layers.2.bias (4,)
- transformer.tgt_embed.weight (900, 256)
- transformer.enc_output.weight (256, 256)
- transformer.enc_output.bias (256,)
- transformer.enc_output_norm.weight (256,)
- transformer.enc_output_norm.bias (256,)
- label_enc.weight (80, 256)
-
- Process finished with exit code 0
|